Federated Learning Management
NEW Summer Semester 2025!
Content
AI applications often require more data than a single organization can provide. Federated learning (FL) is an attractive approach to overcome this bottleneck by connecting distributed data sources. Instead of exchanging raw data, collaborators process their data locally and only share insights in the form of AI models. So far, this technology is mainly established in smartphones, but it promises great potential to drive AI adoption in various industries and optimize AI solutions across internal units and even multiple organizations. Implementing FL systems requires mastering the combination of AI and distributed systems.
The course is about the management of FL projects and describes the steps of FL implementation in business practice. The focus is on managing the complexity of design decisions in the development of FL systems. In addition, various forms of technology delivery and promising areas of application are discussed. Considering increasing regulations related to data processing and AI solutions, such as the GDPR and the EU AI Act, it is shown how to ensure compliance with ethical principles in the context of FL.
Course Structure
The course consists of a lecture and a seminar. The seminar is mandatory. Students work in groups and can choose between a business and a technical topic.
| Lecture | Content |
| 1 | Orga and relevance of federated learning |
| 2 | Foundations of machine learning and federated learning |
| 3 | Challenges of federated learning in practice |
| 4 | Federated learning project management |
| 5 | Ethical principles in federated learning networks |
Location and Date
- Lecture dates: April 24, May 8, May 15, May 22, June 12
- Time: 1:15 PM – 2:45 PM
- Room: LG 0.424
Course Registration
We have limited capacity so not all students who have registered can be accepted. Please do not send an email for registration. Registration is via StudOn until April 11, 2025.
Available for:
- ReWiFak | International Information Systems | Master of Science
- TechFak | Artificial Intelligence | Master of Science
- NatFak | Data Science | Master of Science
Grading and Exam ID
- Written Exam, 60 min (50%), ID: 74911
- Presentation, 15 min (50%) , ID: 74912